# fileScout
Source: https://docs.file.ai/scout/overview

> Process every element of a file on the path suited to it, and get structured data back.

fileScout

# fileScout

Copy pageCopy page

Process every element of a file on the path suited to it, and get structured data back.

Copy pageCopy page

fileScout turns an uploaded file into structured data. It identifies each **element** in the file (text blocks, tables, charts, images and more) and processes every one on the path suited to it, then fills the fields you define in an AI Schema. Financial reports, claim forms and contracts come back in the same shape every time.

## 

[​

](#how-filescout-processes-a-file)

How fileScout processes a file

1

Map the elements

fileScout reads the file and records each element and where it sits: headings, paragraphs, tables, lists, form fields, charts and graphs, images, logos, signatures, handwriting, stamps and QR codes.

2

Choose a path for each element

Tables keep their rows and columns, text is read with its layout, and visual elements such as charts, photos and stamps are read visually. Scanned pages are read with OCR first. **One file can use several models and tools**, one per kind of element.

3

Skip what carries no data

Running headers and footers are left out, so they cost no processing.

4

Fill your schema

The results from every path come together in the fields of your AI Schema, returned by `GET /v1/files/{fileId}/values`.

**Why it matters:** each element gets the method that reads it best, instead of one model for the whole file, and processing is spent only where an element needs it. That keeps accuracy high on mixed files and token use down. The element breakdown is internal; the API returns the structured values. See it on a real-world file in [Multi-page financial report](/examples/financial-report).

## 

[​

](#what’s-included)

What’s included

Step

What it does

Guide

Upload

Accepts single files, batches, large files in parts and ZIP archives

[Upload files](/ingest/uploads)

Read

AI OCR reads text and tables from every page

[Read text](/ingest/ocr-models)

Extract

AI Schemas fill exactly the fields you define, including line items

[Extract fields](/extract/ai-schemas)

Split and classify

Breaks a bundled file into its parts and labels each by type

[Split and classify](/extract/split-classify)

Results

Read values, get a callback, or sync changes to your warehouse

[Get results](/deliver/callbacks)

## 

[​

](#turn-it-on)

Turn it on

Add `FILE_SCOUT` to `enabledProducts` when you request an upload:

```
curl -X POST "$FILEAI_BASE_URL/files/upload" \
  -H "x-api-key: $FILEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "fileName": "invoice.pdf", "fileType": "application/pdf", "enabledProducts": ["FILE_SCOUT"] }'
```

fileScout cannot be combined with `storageOnly: true`. [Choose products](/ingest/uploads#choose-products) covers the other combinations, including adding fileForensics.

## 

[​

](#how-usage-is-counted)

How usage is counted

fileScout is **metered per page**, counted once processing completes:

File

Pages counted

PDF, Word, PowerPoint, TIFF

Each page

Images (JPEG, PNG, WEBP, HEIC)

1

CSV

1

Excel (XLS, XLSX)

Each worksheet

## 

[​

](#next-steps)

Next steps

## Quickstart

Upload a file and read its values in five minutes.

## Extract fields

Define the fields fileScout fills.

[Previous](/authentication)[

Upload files

Send files to fileAI one at a time, in batches of up to 100, in parts for large files, or as ZIP archives.

Next

](/ingest/uploads)

⌘I

## On this page

*   [How fileScout processes a file](#how-filescout-processes-a-file)
*   [What’s included](#what%E2%80%99s-included)
*   [Turn it on](#turn-it-on)
*   [How usage is counted](#how-usage-is-counted)
*   [Next steps](#next-steps)